Name
Title | ||
|---|---|---|
Weights and structure determination of multiple-input feed-forward neural network activated by Chebyshev polynomials of Class 2 via cross-validation |
Abstract | ||
|---|---|---|
Differing from conventional improvements on backpropagation (BP) neural network, a novel neural network is proposed and investigated in this paper to overcome the BP neural-network weaknesses, which is called the multiple-input feed-forward neural network activated by Chebyshev polynomials of Class 2 (MINN-CP2). In addition, to obtain the optimal number of hidden-layer neurons and the optimal linking weights of the MINN-CP2, the paper develops an algorithm of weights and structure determination (WASD) via cross-validation. Numerical studies show the effectiveness and superior abilities (in terms of approximation and generalization) of the MINN-CP2 equipped with the algorithm of WASD via cross-validation. Moreover, an application to gray image denoising demonstrates the effective implementation and application prospect of the proposed MINN-CP2 equipped with the algorithm of WASD via cross-validation. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1007/s00521-014-1667-0 | Neural Computing and Applications |
Keywords | Field | DocType |
Multiple-input feed-forward neural network,Backpropagation (BP),Weights and structure determination (WASD),Cross-validation,Gray image denoising | Chebyshev polynomials,Mathematical optimization,Feedforward neural network,Image denoising,Artificial intelligence,Artificial neural network,Backpropagation,Cross-validation,Mathematics,Machine learning | Journal |
Volume | Issue | ISSN |
25 | 7-8 | 0941-0643 |
Citations | PageRank | References |
6 | 0.44 | 20 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yunong Zhang | 1 | 2344 | 162.43 |
| Xiaotian Yu | 2 | 20 | 1.80 |
| Dongsheng Guo | 3 | 399 | 31.61 |
| Yonghua Yin | 4 | 69 | 7.58 |
| Zhijun Zhang | 5 | 286 | 31.45 |